A Novel Machine Annotated Balanced Bangla OCR Corpus.
Md Jamiur Rahman RifatMridul BanikNazmul HasanJebun NaharFuad RahmanPublished in: CVIP (2) (2020)
Keyphrases
- manually annotated
- character segmentation
- test set
- optical character recognition
- annotated corpus
- character recognition
- statistical machine translation
- post processing
- relation extraction
- document images
- gray scale images
- hand crafted
- error correction
- batch processing
- preprocessing
- named entities
- scene images
- hand written
- text recognition
- genia corpus
- automatic recognition
- flowshop
- document processing
- printed documents
- named entity recognition
- machine vision
- error rate
- scheduling problem